© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13540
    Prev
    Next
    INDEX
    Explanations

    sexual arousal and explicit content

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects explicit pornographic content, especially graphic sexual actions, body parts, and erotic terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keim
    -1.21
     this
    -1.17
     summer
    -1.11
    ּוֹ
    -1.10
    וּ
    -1.08
     people
    -1.06
     it
    -1.03
     бампер
    -0.99
    </em>
    -0.98
    fin
    -0.95
    POSITIVE LOGITS
    久しぶりの
    1.34
    ׇ
    1.32
    Spesifikasi
    1.24
     сахара
    1.24
    ヌーピー
    1.18
     abriu
    1.16
     белье
    1.16
     homicidio
    1.13
     држа
    1.13
    ṝ
    1.13
    Activations Density 0.151%

    No Known Activations